Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 3.1, p. 5 — a max-norm nonexpansion M_F is compatible with T_M, and M_F ∘ T_M has contraction factor γ

Proved
StableFA.Discounted.theorem_3_1

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

contractionfunction-approximationnonexpansionp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1value-iteration

Let MMM be a finite MDP on nnn states with stochastic transition rows and discount factor 0≤γ<10\le\gamma<10≤γ<1, and let TMT_MTM​ be its parallel value backup operator,

(TMV)(i)=min⁡a∈U(i)(cia+γ∑jpaijV(j)).(T_M V)(i)=\min_{a\in U(i)}\Big(c_{ia}+\gamma\sum_{j}p_{aij}V(j)\Big).(TM​V)(i)=a∈U(i)min​(cia​+γj∑​paij​V(j)).

Let MF:Rn→RnM_F:\mathbb R^n\to\mathbb R^nMF​:Rn→Rn be the mapping of a function approximator, and suppose MFM_FMF​ is a nonexpansion in max norm, ∥MF(Y)−MF(Z)∥≤∥Y−Z∥\|M_F(Y)-M_F(Z)\|\le\|Y-Z\|∥MF​(Y)−MF​(Z)∥≤∥Y−Z∥ for all Y,ZY,ZY,Z. Then

  1. MFM_FMF​ is compatible with TMT_MTM​: for every initial guess V0V_0V0​ the iterates (MF∘TM)k(V0)(M_F\circ T_M)^k(V_0)(MF​∘TM​)k(V0​) converge; and
  2. MF∘TMM_F\circ T_MMF​∘TM​ has contraction factor γ\gammaγ: for all V,W∈RnV,W\in\mathbb R^nV,W∈Rn,
∥MF(TMV)−MF(TMW)∥≤γ ∥V−W∥.\|M_F(T_MV)-M_F(T_MW)\|\le\gamma\,\|V-W\| .∥MF​(TM​V)−MF​(TM​W)∥≤γ∥V−W∥.

Approximate value iteration alternates a backup with a fit; this theorem says that any fit that does not expand max-norm distances keeps the combined iteration a contraction.

Formalization Note MFM_FMF​ is an arbitrary map on value functions Fin n → ℝ (not necessarily an averager). The page writes "Let X=S×AX=S\times AX=S×A" and MF∈R∣X∣↦R∣X∣M_F\in\mathbb R^{|X|}\mapsto\mathbb R^{|X|}MF​∈R∣X∣↦R∣X∣; since TMT_MTM​ is the parallel value backup and acts on functions of the state, the composition only makes sense on value functions over the states, which is how it is stated here. ∥⋅∥\|\cdot\|∥⋅∥ on Fin n → ℝ is the max norm.

Preamble
import Mathlib
import Definitions.Def_BertsekasSSPModel
import Definitions.Def_StableFA_Discounted_Setting

open Filter Topology
Formal statement
namespace StableFA.Discounted

theorem theorem_3_1 {n : ℕ} {C : Type} [Fintype C] (M : BertsekasSSPModel n C)
    (γ : ℝ) (hγ0 : 0 ≤ γ) (hγ1 : γ < 1)
    (hp1 : ∀ i, ∀ u ∈ M.U i, ∑ j, M.p i u j = 1)
    (MF : (Fin n → ℝ) → (Fin n → ℝ)) (hMF : ∀ Y Z : Fin n → ℝ, ‖MF Y - MF Z‖ ≤ ‖Y - Z‖) :
    Compatible MF (BertsekasDiscountedBellmanOp M γ) ∧
    ∀ V W : Fin n → ℝ,
      ‖MF (BertsekasDiscountedBellmanOp M γ V) - MF (BertsekasDiscountedBellmanOp M γ W)‖ ≤
        γ * ‖V - W‖ := by sorry

end StableFA.Discounted
Source
Gordon, Stable Function Approximation in Dynamic Programming, Tech. Rep. CMU-CS-95-103, Carnegie Mellon University (1995), p. 5, Theorem 3.1; proof p. 6
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 2026

    Confirmed by the mission captain (proposal self-audit).

View graph

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me